I suspect even some of the more "advanced" queries they demoed off, i.e., "what was that restaurant John and I talked about last week?" also not require LLMs whatsoever and could have been accomplished with a simple search.
I suspect even some of the more "advanced" queries they demoed off, i.e., "what was that restaurant John and I talked about last week?" also not require LLMs whatsoever and could have been accomplished with a simple search.
I think you're going to need some kind of ML to turn that question into a structured search, and interpret the results.
Not necessarily. NLP is possible to do without any ML. See ELIZA [0] as an example, which used pattern matching and substitution to process natural language. A few simple rules can cover a majority of requests. It's still AI, but not ML.
Though I do agree that the ML-based NLP thst we have today is much more usable, albeit more compute-expensive.
[0]: https://en.wikipedia.org/wiki/ELIZA